LSTM-ED for Anomaly Detection in Time Series Data¶
In [ ]:
import time
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import tensorflow as tf
from dataset import *
from plots import *
from metrics import *
from models_funtions import *
# Set style for matplotlib
plt.style.use("Solarize_Light2")
import plotly.io as pio
pio.renderers.default = "notebook_connected"
In [ ]:
# Path to the root directory of the dataset
ROOTDIR_DATASET_NORMAL = '../dataset/normal'
ROOTDIR_DATASET_ANOMALY = '../dataset/collisions'
# TF_ENABLE_ONEDNN_OPTS=0 means that the model will not use the oneDNN library for optimization
import os
os.environ['TF_ENABLE_ONEDNN_OPTS'] = '0'
Variours parameters¶
In [ ]:
#freq = '1.0'
#freq = '0.1'
freq = '0.01'
#freq = '0.005'
file_name_normal = "_20220811_rbtc_"
file_name_collisions = "_collision_20220811_rbtc_"
recording_normal = [0, 2, 3, 4]
recording_collisions = [1, 5]
freq_str = freq.replace(".", "_")
features_folder_normal = f"./features/normal{freq_str}/"
features_folder_collisions = f"./features/collisions{freq_str}/"
Data¶
In [ ]:
df_features_normal, df_normal_raw, _ = get_dataframes(ROOTDIR_DATASET_NORMAL, file_name_normal, recording_normal, freq, f"{features_folder_normal}")
df_features_collisions, df_collisions_raw, df_collisions_raw_action = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, recording_collisions, freq, f"{features_folder_collisions}1_5/")
df_features_collisions_1, df_collisions_raw_1, df_collisions_raw_action_1 = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, [1], freq, f"{features_folder_collisions}1/")
df_features_collisions_5, df_collisions_raw_5, df_collisions_raw_action_5 = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, [5], freq, f"{features_folder_collisions}5/")
Loading data. Found 31 different actions. Loading data done. Loading features from file. --- 0.05327296257019043 seconds --- Loading data. Found 31 different actions. Loading data done. Loading features from file. --- 0.02664017677307129 seconds --- Loading data. Found 31 different actions. Loading data done. Loading features from file. --- 0.0205533504486084 seconds --- Loading data. Found 31 different actions. Loading data done. Loading features from file. --- 0.018580913543701172 seconds ---
In [ ]:
X_train, y_train, X_test, y_test, df_test = get_train_test_data(df_features_normal, df_features_collisions, full_normal=True)
X_train_1, y_train_1, X_test_1, y_test_1, df_test_1 = get_train_test_data(df_features_normal, df_features_collisions_1, full_normal=True)
X_train_5, y_train_5, X_test_5, y_test_5, df_test_5 = get_train_test_data(df_features_normal, df_features_collisions_5, full_normal=True)
c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\sklearn\base.py:493: UserWarning: X does not have valid feature names, but VarianceThreshold was fitted with feature names c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\sklearn\base.py:493: UserWarning: X does not have valid feature names, but VarianceThreshold was fitted with feature names c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\sklearn\base.py:493: UserWarning: X does not have valid feature names, but VarianceThreshold was fitted with feature names
Collisions¶
In [ ]:
collisions_rec1, collisions_init1 = get_collisions('1', ROOTDIR_DATASET_ANOMALY)
collisions_rec5, collisions_init5 = get_collisions('5', ROOTDIR_DATASET_ANOMALY)
# Merge the collisions of the two recordings in one dataframe
collisions_rec = pd.concat([collisions_rec1, collisions_rec5])
collisions_init = pd.concat([collisions_init1, collisions_init5])
In [ ]:
collisions_zones, y_collisions = get_collisions_zones_and_labels(collisions_rec, collisions_init, df_features_collisions)
collisions_zones_1, y_collisions_1 = get_collisions_zones_and_labels(collisions_rec1, collisions_init1, df_features_collisions_1)
collisions_zones_5, y_collisions_5 = get_collisions_zones_and_labels(collisions_rec5, collisions_init5, df_features_collisions_5)
LSTM-AD for Anomaly Detection in Time Series Data¶
In [ ]:
from algorithms.lstm_ad import LSTMAD
def prepare_data_for_lstm(data, len_in):
"""
Prepare data for LSTM-AD by concatenating every len_in rows.
"""
n_features = data.shape[1]
n_samples = data.shape[0] // len_in
prepared_data = data.iloc[:n_samples * len_in].values.reshape(n_samples, -1)
return pd.DataFrame(prepared_data, index=data.index[len_in-1:len_in*n_samples:len_in])
# CURRENTLY FUCKS UP FOR VALUES OF LEN_IN AND LEN_OUT DIFFERENT FROM 1
len_in = 1
X_train_lstm = prepare_data_for_lstm(X_train, len_in)
print(X_train_lstm.shape)
classifier = LSTMAD(
len_in=len_in, # Input sequence length
len_out=1, # Output sequence length (prediction horizon)
num_epochs=100, # Number of training epochs
lr=1e-2, # Learning rate
batch_size=1, # Batch size (usually 1 for time series)
seed=42, # Random seed for reproducibility
gpu=None, # Set to None for CPU, or specify GPU index if available
details=True # Set to True to get detailed predictions
)
# Train the LSTM on normal data
classifier.fit(X_train_lstm)
print("LSTM-AD training completed.")
(973, 118)
100%|██████████| 100/100 [00:54<00:00, 1.82it/s]
LSTM-AD training completed.
Predictions¶
In [ ]:
df_test = get_statistics(X_test, y_collisions, classifier, df_test, freq, threshold_type="mad")
df_test_1 = get_statistics(X_test_1, y_collisions_1, classifier, df_test_1, freq, threshold_type="mad")
df_test_5 = get_statistics(X_test_5, y_collisions_5, classifier, df_test_5, freq, threshold_type="mad")
Anomaly prediction completed.
Number of anomalies detected: 3 with threshold 320189.10040908743, std
Number of anomalies detected: 99 with threshold 4352.728189752417, mad
Number of anomalies detected: 16 with threshold 19752.09464404346, percentile
Number of anomalies detected: 11 with threshold 22140.065470155492, IQR
Number of anomalies detected: 306 with threshold 0.0, zero
choosen threshold type: mad, with value: 4352.7282
F1 Score: 0.8431
Accuracy: 0.8954
Precision: 0.8687
Recall: 0.8190
precision recall f1-score support
0 0.91 0.94 0.92 201
1 0.87 0.82 0.84 105
accuracy 0.90 306
macro avg 0.89 0.88 0.88 306
weighted avg 0.89 0.90 0.89 306
ROC AUC Score: 0.9391
Anomalies detected: 99
Best threshold: 2000.9874 | F1 Score: 0.8465 | Precision: 0.7500 | Recall: 0.9714
Anomalies detected with best threshold: 136
-------------------------------------------------------------------------------------
Anomaly prediction completed.
Number of anomalies detected: 1 with threshold 246703.38367839003, std
Number of anomalies detected: 49 with threshold 2064.64320739006, mad
Number of anomalies detected: 9 with threshold 13631.286312833798, percentile
Number of anomalies detected: 21 with threshold 5775.268781973501, IQR
Number of anomalies detected: 164 with threshold 0.0, zero
choosen threshold type: mad, with value: 2064.6432
F1 Score: 0.7381
Accuracy: 0.8659
Precision: 0.6327
Recall: 0.8857
precision recall f1-score support
0 0.97 0.86 0.91 129
1 0.63 0.89 0.74 35
accuracy 0.87 164
macro avg 0.80 0.87 0.82 164
weighted avg 0.89 0.87 0.87 164
ROC AUC Score: 0.9243
c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\src\models_funtions.py:67: RuntimeWarning: invalid value encountered in divide
Anomalies detected: 49
Best threshold: 1963.6958 | F1 Score: 0.7674 | Precision: 0.6471 | Recall: 0.9429
Anomalies detected with best threshold: 51
-------------------------------------------------------------------------------------
Anomaly prediction completed.
Number of anomalies detected: 2 with threshold 391549.0211743849, std
Number of anomalies detected: 11 with threshold 18920.457281060368, mad
Number of anomalies detected: 8 with threshold 21480.948372360093, percentile
Number of anomalies detected: 2 with threshold 31557.158635700933, IQR
Number of anomalies detected: 141 with threshold 0.0, zero
choosen threshold type: mad, with value: 18920.4573
F1 Score: 0.2090
Accuracy: 0.6241
Precision: 0.6364
Recall: 0.1250
precision recall f1-score support
0 0.62 0.95 0.75 85
1 0.64 0.12 0.21 56
accuracy 0.62 141
macro avg 0.63 0.54 0.48 141
weighted avg 0.63 0.62 0.54 141
ROC AUC Score: 0.8895
c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\src\models_funtions.py:67: RuntimeWarning: invalid value encountered in divide
Anomalies detected: 11 Best threshold: 6321.9896 | F1 Score: 0.8594 | Precision: 0.7639 | Recall: 0.9821 Anomalies detected with best threshold: 72 -------------------------------------------------------------------------------------
c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\src\models_funtions.py:67: RuntimeWarning: invalid value encountered in divide
In [ ]:
plot_anomalies_true_and_predicted(df_collisions_raw, df_collisions_raw_action, collisions_zones, df_test, title="Collisions zones vs predicted zones for both recordings")
In [ ]:
plot_anomalies_true_and_predicted(df_collisions_raw_1, df_collisions_raw_action_1, collisions_zones_1, df_test_1, title="Collisions zones vs predicted zones for recording 1")